What is deliberately wrong with world-indicators

What is deliberately wrong with world-indicators.

720 rows, 9 columns, one row per country per year. A tidy panel of thirty countries over twenty-four years with GDP per capita, life expectancy, population, CO₂ and internet penetration — small enough to hold in your head, rich enough for real modelling.

This is the dataset to reach for when you want to practise small-multiples, animated scatter plots, or fixed-effects regression. It contains a genuine Simpson's paradox: pooled across all countries, internet penetration correlates negatively with growth in life expectancy, while within every single country the relationship is positive.

Something to try: Find the Simpson's paradox and explain it with a small-multiples panel. The SQL playground has it loaded already, and the data explorer will profile every column in one pass if you would rather look before you query.

select *
from world_indicators
limit 20;

The file is generated from a fixed seed, so the CSV you download today is byte-identical to the one from last year. That matters more than it sounds: it means a lesson can say "row 412 is the interesting one" and still be right in eighteen months.

Download it, break it, keep it. CC0 — no attribution required, no account, no email.